linux-kernel - [PATCH v2 1/2] memcg: introduce kfuncs for fetching memcg stats

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20251015190813.80163-2-inwardvessel@gmail.com>
Date: Wed, 15 Oct 2025 12:08:12 -0700
From: JP Kobryn <inwardvessel@...il.com>
To: shakeel.butt@...ux.dev,
	andrii@...nel.org,
	ast@...nel.org,
	mkoutny@...e.com,
	yosryahmed@...gle.com,
	hannes@...xchg.org,
	tj@...nel.org,
	akpm@...ux-foundation.org
Cc: linux-kernel@...r.kernel.org,
	cgroups@...r.kernel.org,
	linux-mm@...ck.org,
	bpf@...r.kernel.org,
	kernel-team@...a.com
Subject: [PATCH v2 1/2] memcg: introduce kfuncs for fetching memcg stats

Reading from the memory.stat file can be expensive because of the string
encoding/decoding and text filtering involved. Introduce three kfuncs for
fetching each type of memcg stat from a bpf program. This allows data to be
transferred directly to userspace, eliminating the need for string
encoding/decoding. It also removes the need for text filtering since it
allows for fetching specific stats.

The patch also includes a kfunc for flushing stats in order to read the
latest values. Note that this is not required for fetching stats, since the
kernel periodically flushes memcg stats. It is left up to the programmer
whether they want more recent stats or not.

Signed-off-by: JP Kobryn <inwardvessel@...il.com>
---
 mm/memcontrol.c | 67 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 67 insertions(+)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4deda33625f4..6547c27d4430 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -871,6 +871,73 @@ unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
 }
 #endif
 
+static inline struct mem_cgroup *memcg_from_cgroup(struct cgroup *cgrp)
+{
+	return cgrp ? mem_cgroup_from_css(cgrp->subsys[memory_cgrp_id]) : NULL;
+}
+
+__bpf_kfunc static void memcg_flush_stats(struct cgroup *cgrp)
+{
+	struct mem_cgroup *memcg = memcg_from_cgroup(cgrp);
+
+	if (!memcg)
+		return;
+
+	mem_cgroup_flush_stats(memcg);
+}
+
+__bpf_kfunc static unsigned long memcg_stat_fetch(struct cgroup *cgrp,
+		enum memcg_stat_item item)
+{
+	struct mem_cgroup *memcg = memcg_from_cgroup(cgrp);
+
+	if (!memcg)
+		return 0;
+
+	return memcg_page_state_output(memcg, item);
+}
+
+__bpf_kfunc static unsigned long memcg_node_stat_fetch(struct cgroup *cgrp,
+		enum node_stat_item item)
+{
+	struct mem_cgroup *memcg = memcg_from_cgroup(cgrp);
+
+	if (!memcg)
+		return 0;
+
+	return memcg_page_state_output(memcg, item);
+}
+
+__bpf_kfunc static unsigned long memcg_vm_event_fetch(struct cgroup *cgrp,
+		enum vm_event_item item)
+{
+	struct mem_cgroup *memcg = memcg_from_cgroup(cgrp);
+
+	if (!memcg)
+		return 0;
+
+	return memcg_events(memcg, item);
+}
+
+BTF_KFUNCS_START(bpf_memcontrol_kfunc_ids)
+BTF_ID_FLAGS(func, memcg_flush_stats, KF_TRUSTED_ARGS | KF_SLEEPABLE)
+BTF_ID_FLAGS(func, memcg_stat_fetch, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, memcg_node_stat_fetch, KF_TRUSTED_ARGS)
+BTF_ID_FLAGS(func, memcg_vm_event_fetch, KF_TRUSTED_ARGS)
+BTF_KFUNCS_END(bpf_memcontrol_kfunc_ids)
+
+static const struct btf_kfunc_id_set bpf_memcontrol_kfunc_set = {
+	.owner          = THIS_MODULE,
+	.set            = &bpf_memcontrol_kfunc_ids,
+};
+
+static int __init bpf_memcontrol_kfunc_init(void)
+{
+	return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC,
+					 &bpf_memcontrol_kfunc_set);
+}
+late_initcall(bpf_memcontrol_kfunc_init);
+
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 {
 	/*
-- 
2.47.3